Jianan Xie

Despite high rationale identification, search-augmented models struggle with refusal, achieving only 42.9% correct halting on unanswerable multi-hop questions.

EviSD achieves state-of-the-art performance in question-answering tasks by leveraging privileged evidence, outperforming existing methods while maintaining efficiency in response generation.

Open-source CPUs can now get near-AMX-level AI acceleration with a matrix extension that's both configurable and decoupled from the core pipeline, slashing design overhead.